{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:10:39Z","timestamp":1776679839916,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570775","type":"print"},{"value":"9789819570782","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-7078-2_2","type":"book-chapter","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:29:45Z","timestamp":1776677385000},"page":"19-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GAM: A Generative Autoencoder for\u00a0Diverse Human Motion Prediction"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8043-227X","authenticated-orcid":false,"given":"Jiapeng","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7698-2173","authenticated-orcid":false,"given":"Hua","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8229-0317","authenticated-orcid":false,"given":"Yaqing","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3776-9799","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Cao, P., Hilliges, O.: A spatio-temporal transformer for 3D human motion prediction. In: 2021 International Conference on 3D Vision (3DV), pp. 565\u2013574. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00066"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Barquero, G., Escalera, S., Palmero, C.: Belfusion: latent diffusion for behavior-driven human motion prediction. arXiv preprint arXiv:2211.14304 (2022)","DOI":"10.1109\/ICCV51070.2023.00220"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Barsoum, E., Kender, J., Liu, Z.: Hp-GAN: Probabilistic 3D human motion prediction via gan. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1418\u20131427 (2018)","DOI":"10.1109\/CVPRW.2018.00191"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., et\u00a0al.: A unified 3D human motion synthesis model via conditional variational auto-encoder. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11645\u201311655 (2021)","DOI":"10.1109\/ICCV48922.2021.01144"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Dang, L., Nie, Y., Long, C., Zhang, Q., Li, G.: Diverse human motion prediction via gumbel-softmax sampling from an auxiliary space. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5162\u20135171 (2022)","DOI":"10.1145\/3503161.3547956"},{"key":"2_CR6","unstructured":"Ghosh, P., Sajjadi, M.S., Vergari, A., Black, M., Sch\u00f6lkopf, B.: From variational to deterministic autoencoders. arXiv preprint arXiv:1903.12436 (2019)"},{"key":"2_CR7","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"2_CR8","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces (2021)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Gu, T., et al.: Stochastic trajectory prediction via motion indeterminacy diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17113\u201317122 (2022)","DOI":"10.1109\/CVPR52688.2022.01660"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Gui, L.Y., Wang, Y.X., Liang, X., Moura, J.M.: Adversarial geometry-aware human motion prediction. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 786\u2013803 (2018)","DOI":"10.1007\/978-3-030-01225-0_48"},{"key":"2_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Hua, Y., et al.: Deterministic-to-stochastic diverse latent feature mapping for human motion synthesis. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pp. 22724\u201322734 (2025)","DOI":"10.1109\/CVPR52734.2025.02116"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hua, Y., Liu, W., Xu, G., Hou, Y., Ong, Y.S., Zhang, Q.: Deterministic-to-stochastic diverse latent feature mapping for human motion synthesis. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 22724\u201322734 (2025)","DOI":"10.1109\/CVPR52734.2025.02116"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"2_CR15","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: Motiongpt: human motion as a foreign language. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"issue":"5","key":"2_CR16","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1007\/s11263-022-01594-9","volume":"130","author":"Y Kong","year":"2022","unstructured":"Kong, Y., Fu, Y.: Human action recognition and prediction: a survey. Int. J. Comput. Vision 130(5), 1366\u20131401 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR17","unstructured":"Lin, X., Amer, M.R.: Human motion modeling using DVGANS (2018)"},{"issue":"4","key":"2_CR18","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/3386569.3392422","volume":"39","author":"HY Ling","year":"2020","unstructured":"Ling, H.Y., Zinno, F., Cheng, G., Van De Panne, M.: Character controllers using motion VAES. ACM Trans. Graphics (TOG) 39(4), 40\u20131 (2020)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Mallya, A., Wang, T.C., Sapra, K., Liu, M.Y.: World-consistent video-to-video synthesis. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part VIII 16, pp. 359\u2013378. Springer (2020)","DOI":"10.1007\/978-3-030-58598-3_22"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M.: History repeats itself: human motion prediction via motion attention. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16, pp. 474\u2013489. Springer (2020)","DOI":"10.1007\/978-3-030-58568-6_28"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M.: Generating smooth pose sequences for diverse human motion prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13309\u201313318 (2021)","DOI":"10.1109\/ICCV48922.2021.01306"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Mao, W., Liu, M., Salzmann, M., Li, H.: Learning trajectory dependencies for human motion prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9489\u20139497 (2019)","DOI":"10.1109\/ICCV.2019.00958"},{"key":"2_CR23","unstructured":"Mehta, H., Gupta, A., Cutkosky, A., Neyshabur, B.: Long range language modeling via gated state spaces. arXiv preprint arXiv:2206.13947 (2022)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O.J., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13653\u201313662 (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"issue":"1","key":"2_CR26","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-009-0273-6","volume":"87","author":"L Sigal","year":"2010","unstructured":"Sigal, L., Balan, A.O., Black, M.J.: Humaneva: Synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. Int. J. Comput. Vision 87(1), 4\u201327 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR27","unstructured":"Smith, J.T., Warrington, A., Linderman, S.W.: Simplified state space layers for sequence modeling. arXiv preprint arXiv:2208.04933 (2022)"},{"key":"2_CR28","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.: Human motion diffusion model. arxiv 2022. arXiv preprint arXiv:2209.14916"},{"key":"2_CR29","unstructured":"Wei, D., et al.: Human joint kinematics diffusion-refinement for stochastic motion prediction. arXiv preprint arXiv:2210.05976 (2022)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Wei, D., et al.: Human joint kinematics diffusion-refinement for stochastic motion prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 6110\u20136118 (2023)","DOI":"10.1609\/aaai.v37i5.25754"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Yan, X., et al.: Mt-VAE: learning motion transformations to generate multimodal human dynamics. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 265\u2013281 (2018)","DOI":"10.1007\/978-3-030-01228-1_17"},{"issue":"10","key":"2_CR32","doi-asserted-by":"publisher","first-page":"5707","DOI":"10.1109\/TCSVT.2023.3255186","volume":"33","author":"H Yu","year":"2023","unstructured":"Yu, H., et al.: Toward realistic 3D human motion prediction with a spatio-temporal cross-transformer approach. IEEE Trans. Circuits Syst. Video Technol. 33(10), 5707\u20135720 (2023)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Yu, H., Hou, Y., Pei, W., Ong, Y.S., Zhang, Q.: Divdiff: a conditional diffusion model for diverse human motion prediction. IEEE Trans. Multimedia (2024)","DOI":"10.1109\/TMM.2024.3521821"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Yu, H., et al.: Towards efficient and diverse generative model for unconditional human motion synthesis. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 2535\u20132544 (2024)","DOI":"10.1145\/3664647.3681093"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Kitani, K.: Dlow: Diversifying latent flows for diverse human motion prediction. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part IX 16, pp. 346\u2013364. Springer (2020)","DOI":"10.1007\/978-3-030-58545-7_20"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Black, M.J., Tang, S.: We are more than our joints: Predicting how 3D bodies move. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3372\u20133382 (2021)","DOI":"10.1109\/CVPR46437.2021.00338"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7078-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:30:14Z","timestamp":1776677414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7078-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570775","9789819570782"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7078-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"21 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}